Method of and apparatus for improving productivity of human reviewers of automatically transcribed documents generated by media conversion systems
First Claim
1. An apparatus for improving productivity of human review of an automatically transcribed document generated by a speech-to-text conversion system, wherein the document is generated from an audio recording recorded by an author, the apparatus comprising:
- a. a controller coupled to the speech-to-text conversion system for selecting an appropriate one of a plurality of human reviewers to review the document wherein, the controller is capable of extracting an attribute from the document representative of a content of the document and further wherein the controller stores a plurality of reviewer profiles corresponding to each one of the human reviewers and provides the selected reviewer in response to the attribute;
b. a transmission device coupled to the controller for transmitting the document and the audio recording to the selected reviewer;
c. means for analyzing the transcription to associate portions of the transcription with a plurality of confidence levels of transcription accuracy, wherein each portion is marked according to one of the plurality of confidence levels;
d. means for selecting one of the portions of the document in response to a command from the reviewer; and
e. means for playing a portion of the voice recording corresponding to a selected portion of the transcription.
19 Assignments
0 Petitions
Accused Products
Abstract
An apparatus for improving productivity of human reviewers of transcribed documents generated by media conversion systems includes a server/client network of computers, memories and file systems. The server receives and stores voice files created by users of the system. The server is configured for coupling to a speech-to-text media conversion system to receive converted text files of the audio voice files. The server analyzes the converted text files and routes the converted files to the appropriate reviewers according to an adaptive algorithm. The converted files are displayed on the assigned reviewer'"'"'s screen at the reviewer'"'"'s workstation. To aid the reviewer in pinpointing potential errors, the workstation displays different segments of the converted files in different colors to reflect different confidence levels of transcription accuracy. Portions of the original voice message that correspond to the potential errors are played back for the reviewer. The reviewers'"'"' workstations also perform productivity enhancing functions such as spelling and grammar checking. After the reviewer has made all the necessary corrections, the reviewed files are transmitted back to the server to be stored and accessed by the users. A user database in the server is also updated to store recurrent user-specific errors corrected by the reviewer. A language analysis system is also disposed to adaptively correct user-specific errors in future reviews according to the information in the user database.
-
Citations
36 Claims
-
1. An apparatus for improving productivity of human review of an automatically transcribed document generated by a speech-to-text conversion system, wherein the document is generated from an audio recording recorded by an author, the apparatus comprising:
-
a. a controller coupled to the speech-to-text conversion system for selecting an appropriate one of a plurality of human reviewers to review the document wherein, the controller is capable of extracting an attribute from the document representative of a content of the document and further wherein the controller stores a plurality of reviewer profiles corresponding to each one of the human reviewers and provides the selected reviewer in response to the attribute; b. a transmission device coupled to the controller for transmitting the document and the audio recording to the selected reviewer; c. means for analyzing the transcription to associate portions of the transcription with a plurality of confidence levels of transcription accuracy, wherein each portion is marked according to one of the plurality of confidence levels; d. means for selecting one of the portions of the document in response to a command from the reviewer; and e. means for playing a portion of the voice recording corresponding to a selected portion of the transcription. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. An apparatus for improving productivity of human review of an automatically transcribed output generated by an information processing system, wherein the output is generated in response to an input, the apparatus comprising:
-
a. means for extracting an attribute from an automatically transcribed output generated by an information processing system in response to an input; b. means for selecting a specific one human reviewer from among a plurality of human reviewers based on the attribute; c. means for analyzing the output to associate portions of the output with a plurality of confidence levels of transcription accuracy; and d. means for marking each portion of the output according to a corresponding one of the plurality of confidence levels. - View Dependent Claims (13, 14, 15, 16, 17)
-
-
18. An apparatus for facilitating review of an automatically transcribed document generated by a media conversion system, wherein the document is generated in response to an input, the apparatus comprising:
-
a. means for extracting a keyword from the document, wherein the keyword is determined by comparing the document to a database of keywords; b means for selecting a specific one reviewer from among a plurality of reviewers in response to the keyword; c. means for transmitting the input and the document to the selected reviewer for review; d. means for analyzing the document to associate portions of the document with a plurality of confidence levels of transcription accuracy; and e. means for marking each portion of the document according to a corresponding one of the plurality of confidence levels. - View Dependent Claims (19, 20, 21, 22, 23, 24, 25, 26, 27, 28)
-
-
29. A method of improving productivity of human review of an automatically transcribed document generated by an information processing system, wherein the document is generated in response to an input, the method comprising the steps of:
-
a. extracting an attribute from the document, wherein the attribute is determined by comparing the document to a database of keywords; b. selecting a specific one human reviewer from among a plurality of human reviewers based on the attribute; c. analyzing the document to associate portions of the document with a plurality of confidence levels of transcription accuracy; and d. marking each portion of the document according to a corresponding one of the plurality of confidence levels. - View Dependent Claims (30, 31, 32, 33, 34, 35, 36)
-
Specification